From ff92741270bf8b6e78aa885f166b68c7a67ab13a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 11:48:15 +0200 Subject: net: introduce name_node struct to be used in hashlist Introduce name_node structure to hold name of device and put it into hashlist instead of putting there struct net_device directly. Add a necessary infrastructure to manipulate the hashlist. This prepares the code to use the same hashlist for alternative names introduced later in this set. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9eda1c31d1f7..e92bc5467256 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -925,6 +925,12 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; +struct netdev_name_node { + struct hlist_node hlist; + struct net_device *dev; + const char *name; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1564,7 +1570,7 @@ enum netdev_priv_flags { * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. * - * @name_hlist: Device name hash chain, please keep it close to name[] + * @name_node: Name hashlist node * @ifalias: SNMP alias * @mem_end: Shared memory end * @mem_start: Shared memory start @@ -1774,7 +1780,7 @@ enum netdev_priv_flags { struct net_device { char name[IFNAMSIZ]; - struct hlist_node name_hlist; + struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; /* * I/O specific fields -- cgit v1.2.3 From 36fbf1e52bd3ff8a5cb604955eedfc9350c2e6cc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 11:48:16 +0200 Subject: net: rtnetlink: add linkprop commands to add and delete alternative ifnames Add two commands to add and delete list of link properties. Implement the first property type along - alternative ifnames. Each net device can have multiple alternative names. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++ include/uapi/linux/if.h | 1 + include/uapi/linux/if_link.h | 2 + include/uapi/linux/rtnetlink.h | 7 +++ net/core/dev.c | 58 ++++++++++++++++++++++- net/core/rtnetlink.c | 103 +++++++++++++++++++++++++++++++++++++++++ security/selinux/nlmsgtab.c | 4 +- 7 files changed, 177 insertions(+), 2 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e92bc5467256..48cc71aae466 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -927,10 +927,14 @@ struct tlsdev_ops; struct netdev_name_node { struct hlist_node hlist; + struct list_head list; struct net_device *dev; const char *name; }; +int netdev_name_node_alt_create(struct net_device *dev, const char *name); +int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index 7fea0fd7d6f5..4bf33344aab1 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -33,6 +33,7 @@ #define IFNAMSIZ 16 #endif /* __UAPI_DEF_IF_IFNAMSIZ */ #define IFALIASZ 256 +#define ALTIFNAMSIZ 128 #include /* For glibc compatibility. An empty enum does not compile. */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4a8c02cafa9a..8aec8769d944 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -167,6 +167,8 @@ enum { IFLA_NEW_IFINDEX, IFLA_MIN_MTU, IFLA_MAX_MTU, + IFLA_PROP_LIST, + IFLA_ALT_IFNAME, /* Alternative ifname */ __IFLA_MAX }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index ce2a623abb75..1418a8362bb7 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -164,6 +164,13 @@ enum { RTM_GETNEXTHOP, #define RTM_GETNEXTHOP RTM_GETNEXTHOP + RTM_NEWLINKPROP = 108, +#define RTM_NEWLINKPROP RTM_NEWLINKPROP + RTM_DELLINKPROP, +#define RTM_DELLINKPROP RTM_DELLINKPROP + RTM_GETLINKPROP, +#define RTM_GETLINKPROP RTM_GETLINKPROP + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; diff --git a/net/core/dev.c b/net/core/dev.c index d2053d07c94a..7a456c6a7ad8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -245,7 +245,13 @@ static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, static struct netdev_name_node * netdev_name_node_head_alloc(struct net_device *dev) { - return netdev_name_node_alloc(dev, dev->name); + struct netdev_name_node *name_node; + + name_node = netdev_name_node_alloc(dev, dev->name); + if (!name_node) + return NULL; + INIT_LIST_HEAD(&name_node->list); + return name_node; } static void netdev_name_node_free(struct netdev_name_node *name_node) @@ -289,6 +295,55 @@ static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, return NULL; } +int netdev_name_node_alt_create(struct net_device *dev, const char *name) +{ + struct netdev_name_node *name_node; + struct net *net = dev_net(dev); + + name_node = netdev_name_node_lookup(net, name); + if (name_node) + return -EEXIST; + name_node = netdev_name_node_alloc(dev, name); + if (!name_node) + return -ENOMEM; + netdev_name_node_add(net, name_node); + /* The node that holds dev->name acts as a head of per-device list. */ + list_add_tail(&name_node->list, &dev->name_node->list); + + return 0; +} +EXPORT_SYMBOL(netdev_name_node_alt_create); + +static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) +{ + list_del(&name_node->list); + netdev_name_node_del(name_node); + kfree(name_node->name); + netdev_name_node_free(name_node); +} + +int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) +{ + struct netdev_name_node *name_node; + struct net *net = dev_net(dev); + + name_node = netdev_name_node_lookup(net, name); + if (!name_node) + return -ENOENT; + __netdev_name_node_alt_destroy(name_node); + + return 0; +} +EXPORT_SYMBOL(netdev_name_node_alt_destroy); + +static void netdev_name_node_alt_flush(struct net_device *dev) +{ + struct netdev_name_node *name_node, *tmp; + + list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) + __netdev_name_node_alt_destroy(name_node); +} + /* Device list insertion */ static void list_netdevice(struct net_device *dev) { @@ -8317,6 +8372,7 @@ static void rollback_registered_many(struct list_head *head) dev_uc_flush(dev); dev_mc_flush(dev); + netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); if (dev->netdev_ops->ndo_uninit) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1ee6460f8275..e13646993d82 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1750,6 +1750,9 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 }, [IFLA_MIN_MTU] = { .type = NLA_U32 }, [IFLA_MAX_MTU] = { .type = NLA_U32 }, + [IFLA_PROP_LIST] = { .type = NLA_NESTED }, + [IFLA_ALT_IFNAME] = { .type = NLA_STRING, + .len = ALTIFNAMSIZ - 1 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -3373,6 +3376,103 @@ out: return err; } +static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, + bool *changed, struct netlink_ext_ack *extack) +{ + char *alt_ifname; + int err; + + err = nla_validate(attr, attr->nla_len, IFLA_MAX, ifla_policy, extack); + if (err) + return err; + + alt_ifname = nla_data(attr); + if (cmd == RTM_NEWLINKPROP) { + alt_ifname = kstrdup(alt_ifname, GFP_KERNEL); + if (!alt_ifname) + return -ENOMEM; + err = netdev_name_node_alt_create(dev, alt_ifname); + if (err) { + kfree(alt_ifname); + return err; + } + } else if (cmd == RTM_DELLINKPROP) { + err = netdev_name_node_alt_destroy(dev, alt_ifname); + if (err) + return err; + } else { + WARN_ON(1); + return 0; + } + + *changed = true; + return 0; +} + +static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + struct ifinfomsg *ifm; + bool changed = false; + struct nlattr *attr; + int err, rem; + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack); + if (err) + return err; + + err = rtnl_ensure_unique_netns(tb, extack, true); + if (err) + return err; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index > 0) { + dev = __dev_get_by_index(net, ifm->ifi_index); + } else if (tb[IFLA_IFNAME]) { + char ifname[IFNAMSIZ]; + + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, ifname); + } else { + return -EINVAL; + } + + if (!dev) + return -ENODEV; + + if (!tb[IFLA_PROP_LIST]) + return 0; + + nla_for_each_nested(attr, tb[IFLA_PROP_LIST], rem) { + switch (nla_type(attr)) { + case IFLA_ALT_IFNAME: + err = rtnl_alt_ifname(cmd, dev, attr, &changed, extack); + if (err) + return err; + break; + } + } + + if (changed) + netdev_state_change(dev); + return 0; +} + +static int rtnl_newlinkprop(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + return rtnl_linkprop(RTM_NEWLINKPROP, skb, nlh, extack); +} + +static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack); +} + static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); @@ -5331,6 +5431,9 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, 0); rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, 0); + rtnl_register(PF_UNSPEC, RTM_NEWLINKPROP, rtnl_newlinkprop, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELLINKPROP, rtnl_dellinkprop, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0); rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0); rtnl_register(PF_BRIDGE, RTM_GETNEIGH, rtnl_fdb_get, rtnl_fdb_dump, 0); diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 58345ba0528e..c97fdae8f71b 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -83,6 +83,8 @@ static const struct nlmsg_perm nlmsg_route_perms[] = { RTM_NEWNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_NEWLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_DELLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, }; static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = @@ -166,7 +168,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) * structures at the top of this file with the new mappings * before updating the BUILD_BUG_ON() macro! */ - BUILD_BUG_ON(RTM_MAX != (RTM_NEWNEXTHOP + 3)); + BUILD_BUG_ON(RTM_MAX != (RTM_NEWLINKPROP + 3)); err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms, sizeof(nlmsg_route_perms)); break; -- cgit v1.2.3 From afa0df5998131153ec3036f41e76ece33bf1334f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 10:15:09 +0200 Subject: net: push loops and nb calls into helper functions Push iterations over net namespaces and netdevices from register_netdevice_notifier() and unregister_netdevice_notifier() into helper functions. Along with that introduce continue_reverse macros to make the code a bit nicer allowing to get rid of "last" marks. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++ include/net/net_namespace.h | 3 +- net/core/dev.c | 89 +++++++++++++++++++++++++++++++-------------- 3 files changed, 66 insertions(+), 29 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 48cc71aae466..7b183f724fc4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2574,6 +2574,9 @@ extern rwlock_t dev_base_lock; /* Device list lock */ list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue(net, d) \ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) +#define for_each_netdev_continue_reverse(net, d) \ + list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \ + dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index f8712bbeb2e0..c5a98e03591d 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -317,7 +317,8 @@ static inline struct net *read_pnet(const possible_net_t *pnet) /* Protected by net_rwsem */ #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) - +#define for_each_net_continue_reverse(VAR) \ + list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) #define for_each_net_rcu(VAR) \ list_for_each_entry_rcu(VAR, &net_namespace_list, list) diff --git a/net/core/dev.c b/net/core/dev.c index 7a456c6a7ad8..a8b70cb6c732 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1725,6 +1725,62 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, return nb->notifier_call(nb, val, &info); } +static int call_netdevice_register_notifiers(struct notifier_block *nb, + struct net_device *dev) +{ + int err; + + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); + err = notifier_to_errno(err); + if (err) + return err; + + if (!(dev->flags & IFF_UP)) + return 0; + + call_netdevice_notifier(nb, NETDEV_UP, dev); + return 0; +} + +static void call_netdevice_unregister_notifiers(struct notifier_block *nb, + struct net_device *dev) +{ + if (dev->flags & IFF_UP) { + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); + } + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); +} + +static int call_netdevice_register_net_notifiers(struct notifier_block *nb, + struct net *net) +{ + struct net_device *dev; + int err; + + for_each_netdev(net, dev) { + err = call_netdevice_register_notifiers(nb, dev); + if (err) + goto rollback; + } + return 0; + +rollback: + for_each_netdev_continue_reverse(net, dev) + call_netdevice_unregister_notifiers(nb, dev); + return err; +} + +static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, + struct net *net) +{ + struct net_device *dev; + + for_each_netdev(net, dev) + call_netdevice_unregister_notifiers(nb, dev); +} + static int dev_boot_phase = 1; /** @@ -1743,8 +1799,6 @@ static int dev_boot_phase = 1; int register_netdevice_notifier(struct notifier_block *nb) { - struct net_device *dev; - struct net_device *last; struct net *net; int err; @@ -1757,17 +1811,9 @@ int register_netdevice_notifier(struct notifier_block *nb) if (dev_boot_phase) goto unlock; for_each_net(net) { - for_each_netdev(net, dev) { - err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); - err = notifier_to_errno(err); - if (err) - goto rollback; - - if (!(dev->flags & IFF_UP)) - continue; - - call_netdevice_notifier(nb, NETDEV_UP, dev); - } + err = call_netdevice_register_net_notifiers(nb, net); + if (err) + goto rollback; } unlock: @@ -1776,22 +1822,9 @@ unlock: return err; rollback: - last = dev; - for_each_net(net) { - for_each_netdev(net, dev) { - if (dev == last) - goto outroll; - - if (dev->flags & IFF_UP) { - call_netdevice_notifier(nb, NETDEV_GOING_DOWN, - dev); - call_netdevice_notifier(nb, NETDEV_DOWN, dev); - } - call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); - } - } + for_each_net_continue_reverse(net) + call_netdevice_unregister_net_notifiers(nb, net); -outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } -- cgit v1.2.3 From a30c7b429f2dd980202c912fcb76442364937b4d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 10:15:10 +0200 Subject: net: introduce per-netns netdevice notifiers Often the code for example in drivers is interested in getting notifier call only from certain network namespace. In addition to the existing global netdevice notifier chain introduce per-netns chains and allow users to register to that. Eventually this would eliminate unnecessary overhead in case there are many netdevices in many network namespaces. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++ include/net/net_namespace.h | 3 ++ net/core/dev.c | 87 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 93 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7b183f724fc4..fe45b2c72315 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2504,6 +2504,9 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd); int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); +int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); +int unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb); struct netdev_notifier_info { struct net_device *dev; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index c5a98e03591d..5ac2bb16d4b3 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -36,6 +36,7 @@ #include #include #include +#include struct user_namespace; struct proc_dir_entry; @@ -96,6 +97,8 @@ struct net { struct list_head dev_base_head; struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; + struct raw_notifier_head netdev_chain; + unsigned int dev_base_seq; /* protected by rtnl_mutex */ int ifindex; unsigned int dev_unreg_count; diff --git a/net/core/dev.c b/net/core/dev.c index a8b70cb6c732..c680225e0da8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1874,6 +1874,80 @@ unlock: } EXPORT_SYMBOL(unregister_netdevice_notifier); +/** + * register_netdevice_notifier_net - register a per-netns network notifier block + * @net: network namespace + * @nb: notifier + * + * Register a notifier to be called when network device events occur. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. + * + * When registered all registration and up events are replayed + * to the new notifier to allow device to have a race free + * view of the network device list. + */ + +int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = raw_notifier_chain_register(&net->netdev_chain, nb); + if (err) + goto unlock; + if (dev_boot_phase) + goto unlock; + + err = call_netdevice_register_net_notifiers(nb, net); + if (err) + goto chain_unregister; + +unlock: + rtnl_unlock(); + return err; + +chain_unregister: + raw_notifier_chain_unregister(&netdev_chain, nb); + goto unlock; +} +EXPORT_SYMBOL(register_netdevice_notifier_net); + +/** + * unregister_netdevice_notifier_net - unregister a per-netns + * network notifier block + * @net: network namespace + * @nb: notifier + * + * Unregister a notifier previously registered by + * register_netdevice_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. + */ + +int unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = raw_notifier_chain_unregister(&net->netdev_chain, nb); + if (err) + goto unlock; + + call_netdevice_unregister_net_notifiers(nb, net); + +unlock: + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(unregister_netdevice_notifier_net); + /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function @@ -1886,7 +1960,18 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); static int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { + struct net *net = dev_net(info->dev); + int ret; + ASSERT_RTNL(); + + /* Run per-netns notifier block chain first, then run the global one. + * Hopefully, one day, the global one is going to be removed after + * all notifier block registrators get converted to be per-netns. + */ + ret = raw_notifier_call_chain(&net->netdev_chain, val, info); + if (ret & NOTIFY_STOP_MASK) + return ret; return raw_notifier_call_chain(&netdev_chain, val, info); } @@ -9785,6 +9870,8 @@ static int __net_init netdev_init(struct net *net) if (net->dev_index_head == NULL) goto err_idx; + RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); + return 0; err_idx: -- cgit v1.2.3 From bacb7e1855969bba78b32302453d2cc8ba0bc403 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Oct 2019 14:20:34 -0700 Subject: Revert "tun: call dev_get_valid_name() before register_netdevice()" This reverts commit 0ad646c81b2182f7fa67ec0c8c825e0ee165696d. As noticed by Jakub, this is no longer needed after commit 11fc7d5a0a2d ("tun: fix memory leak in error path") This no longer exports dev_get_valid_name() for the exclusive use of tun driver. Suggested-by: Jakub Kicinski Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- drivers/net/tun.c | 3 --- include/linux/netdevice.h | 3 --- net/core/dev.c | 5 ++--- 3 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 1e541b08b136..0413d182d782 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2788,9 +2788,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (!dev) return -ENOMEM; - err = dev_get_valid_name(net, dev, name); - if (err < 0) - goto err_free_dev; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fe45b2c72315..3207e0b9ec4e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4113,9 +4113,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs); -int dev_get_valid_name(struct net *net, struct net_device *dev, - const char *name); - #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) diff --git a/net/core/dev.c b/net/core/dev.c index 7d05e042c6ba..8bc3dce71fc0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1249,8 +1249,8 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); -int dev_get_valid_name(struct net *net, struct net_device *dev, - const char *name) +static int dev_get_valid_name(struct net *net, struct net_device *dev, + const char *name) { BUG_ON(!net); @@ -1266,7 +1266,6 @@ int dev_get_valid_name(struct net *net, struct net_device *dev, return 0; } -EXPORT_SYMBOL(dev_get_valid_name); /** * dev_change_name - change name of a device -- cgit v1.2.3 From 5343da4c17429efaa5fb1594ea96aee1a283e694 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:50 +0000 Subject: net: core: limit nested device depth Current code doesn't limit the number of nested devices. Nested devices would be handled recursively and this needs huge stack memory. So, unlimited nested devices could make stack overflow. This patch adds upper_level and lower_level, they are common variables and represent maximum lower/upper depth. When upper/lower device is attached or dettached, {lower/upper}_level are updated. and if maximum depth is bigger than 8, attach routine fails and returns -EMLINK. In addition, this patch converts recursive routine of netdev_walk_all_{lower/upper} to iterator routine. Test commands: ip link add dummy0 type dummy ip link add link dummy0 name vlan1 type vlan id 1 ip link set vlan1 up for i in {2..55} do let A=$i-1 ip link add vlan$i link vlan$A type vlan id $i done ip link del dummy0 Splat looks like: [ 155.513226][ T908] BUG: KASAN: use-after-free in __unwind_start+0x71/0x850 [ 155.514162][ T908] Write of size 88 at addr ffff8880608a6cc0 by task ip/908 [ 155.515048][ T908] [ 155.515333][ T908] CPU: 0 PID: 908 Comm: ip Not tainted 5.4.0-rc3+ #96 [ 155.516147][ T908] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 155.517233][ T908] Call Trace: [ 155.517627][ T908] [ 155.517918][ T908] Allocated by task 0: [ 155.518412][ T908] (stack is not available) [ 155.518955][ T908] [ 155.519228][ T908] Freed by task 0: [ 155.519885][ T908] (stack is not available) [ 155.520452][ T908] [ 155.520729][ T908] The buggy address belongs to the object at ffff8880608a6ac0 [ 155.520729][ T908] which belongs to the cache names_cache of size 4096 [ 155.522387][ T908] The buggy address is located 512 bytes inside of [ 155.522387][ T908] 4096-byte region [ffff8880608a6ac0, ffff8880608a7ac0) [ 155.523920][ T908] The buggy address belongs to the page: [ 155.524552][ T908] page:ffffea0001822800 refcount:1 mapcount:0 mapping:ffff88806c657cc0 index:0x0 compound_mapcount:0 [ 155.525836][ T908] flags: 0x100000000010200(slab|head) [ 155.526445][ T908] raw: 0100000000010200 ffffea0001813808 ffffea0001a26c08 ffff88806c657cc0 [ 155.527424][ T908] raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000 [ 155.528429][ T908] page dumped because: kasan: bad access detected [ 155.529158][ T908] [ 155.529410][ T908] Memory state around the buggy address: [ 155.530060][ T908] ffff8880608a6b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 155.530971][ T908] ffff8880608a6c00: fb fb fb fb fb f1 f1 f1 f1 00 f2 f2 f2 f3 f3 f3 [ 155.531889][ T908] >ffff8880608a6c80: f3 fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 155.532806][ T908] ^ [ 155.533509][ T908] ffff8880608a6d00: fb fb fb fb fb fb fb fb fb f1 f1 f1 f1 00 00 00 [ 155.534436][ T908] ffff8880608a6d80: f2 f3 f3 f3 f3 fb fb fb 00 00 00 00 00 00 00 00 [ ... ] Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 + net/core/dev.c | 272 ++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 231 insertions(+), 45 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9eda1c31d1f7..38c5909e1c35 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1649,6 +1649,8 @@ enum netdev_priv_flags { * @perm_addr: Permanent hw address * @addr_assign_type: Hw address assignment type * @addr_len: Hardware address length + * @upper_level: Maximum depth level of upper devices. + * @lower_level: Maximum depth level of lower devices. * @neigh_priv_len: Used in neigh_alloc() * @dev_id: Used to differentiate devices that share * the same link layer address @@ -1875,6 +1877,8 @@ struct net_device { unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; unsigned char addr_len; + unsigned char upper_level; + unsigned char lower_level; unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; diff --git a/net/core/dev.c b/net/core/dev.c index bf3ed413abaf..ab0edfc4a422 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,6 +146,7 @@ #include "net-sysfs.h" #define MAX_GRO_SKBS 8 +#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -6644,6 +6645,21 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); +static struct net_device *netdev_next_upper_dev(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *upper; + + upper = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->adj_list.upper) + return NULL; + + *iter = &upper->list; + + return upper->dev; +} + static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { @@ -6661,28 +6677,93 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, return upper->dev; } +static int netdev_walk_all_upper_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + + now = dev; + iter = &dev->adj_list.upper; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = netdev_next_upper_dev(now, &iter); + if (!udev) + break; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), void *data) { - struct net_device *udev; - struct list_head *iter; - int ret; + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; - for (iter = &dev->adj_list.upper, - udev = netdev_next_upper_dev_rcu(dev, &iter); - udev; - udev = netdev_next_upper_dev_rcu(dev, &iter)) { - /* first is the upper device itself */ - ret = fn(udev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.upper; - /* then look at all of its upper devices */ - ret = netdev_walk_all_upper_dev_rcu(udev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = netdev_next_upper_dev_rcu(now, &iter); + if (!udev) + break; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; @@ -6790,23 +6871,42 @@ int netdev_walk_all_lower_dev(struct net_device *dev, void *data), void *data) { - struct net_device *ldev; - struct list_head *iter; - int ret; + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; - for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev(dev, &iter); - ldev; - ldev = netdev_next_lower_dev(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.lower; - /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev(ldev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; @@ -6827,28 +6927,93 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } -int netdev_walk_all_lower_dev_rcu(struct net_device *dev, - int (*fn)(struct net_device *dev, - void *data), - void *data) +static u8 __netdev_upper_depth(struct net_device *dev) +{ + struct net_device *udev; + struct list_head *iter; + u8 max_depth = 0; + + for (iter = &dev->adj_list.upper, + udev = netdev_next_upper_dev(dev, &iter); + udev; + udev = netdev_next_upper_dev(dev, &iter)) { + if (max_depth < udev->upper_level) + max_depth = udev->upper_level; + } + + return max_depth; +} + +static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; - int ret; + u8 max_depth = 0; for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev_rcu(dev, &iter); + ldev = netdev_next_lower_dev(dev, &iter); ldev; - ldev = netdev_next_lower_dev_rcu(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + ldev = netdev_next_lower_dev(dev, &iter)) { + if (max_depth < ldev->lower_level) + max_depth = ldev->lower_level; + } - /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data); - if (ret) - return ret; + return max_depth; +} + +static int __netdev_update_upper_level(struct net_device *dev, void *data) +{ + dev->upper_level = __netdev_upper_depth(dev) + 1; + return 0; +} + +static int __netdev_update_lower_level(struct net_device *dev, void *data) +{ + dev->lower_level = __netdev_lower_depth(dev) + 1; + return 0; +} + +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; @@ -7105,6 +7270,9 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; + if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) + return -EMLINK; + if (!master) { if (netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; @@ -7131,6 +7299,12 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) goto rollback; + __netdev_update_upper_level(dev, NULL); + netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL); + return 0; rollback: @@ -7213,6 +7387,12 @@ void netdev_upper_dev_unlink(struct net_device *dev, call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); + + __netdev_update_upper_level(dev, NULL); + netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -9212,6 +9392,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->upper_level = 1; + dev->lower_level = 1; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); -- cgit v1.2.3 From ab92d68fc22f9afab480153bd82a20f6e2533769 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:51 +0000 Subject: net: core: add generic lockdep keys Some interface types could be nested. (VLAN, BONDING, TEAM, MACSEC, MACVLAN, IPVLAN, VIRT_WIFI, VXLAN, etc..) These interface types should set lockdep class because, without lockdep class key, lockdep always warn about unexisting circular locking. In the current code, these interfaces have their own lockdep class keys and these manage itself. So that there are so many duplicate code around the /driver/net and /net/. This patch adds new generic lockdep keys and some helper functions for it. This patch does below changes. a) Add lockdep class keys in struct net_device - qdisc_running, xmit, addr_list, qdisc_busylock - these keys are used as dynamic lockdep key. b) When net_device is being allocated, lockdep keys are registered. - alloc_netdev_mqs() c) When net_device is being free'd llockdep keys are unregistered. - free_netdev() d) Add generic lockdep key helper function - netdev_register_lockdep_key() - netdev_unregister_lockdep_key() - netdev_update_lockdep_key() e) Remove unnecessary generic lockdep macro and functions f) Remove unnecessary lockdep code of each interfaces. After this patch, each interface modules don't need to maintain their lockdep keys. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 1 - drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 18 --- drivers/net/hamradio/bpqether.c | 22 ---- drivers/net/hyperv/netvsc_drv.c | 2 - drivers/net/ipvlan/ipvlan_main.c | 2 - drivers/net/macsec.c | 5 - drivers/net/macvlan.c | 12 -- drivers/net/ppp/ppp_generic.c | 2 - drivers/net/team/team.c | 2 - drivers/net/vrf.c | 1 - drivers/net/wireless/intersil/hostap/hostap_hw.c | 25 ----- include/linux/netdevice.h | 35 +++--- net/8021q/vlan_dev.c | 27 ----- net/batman-adv/soft-interface.c | 32 ------ net/bluetooth/6lowpan.c | 8 -- net/bridge/br_device.c | 8 -- net/core/dev.c | 127 ++++++++-------------- net/core/rtnetlink.c | 1 + net/dsa/master.c | 5 - net/dsa/slave.c | 12 -- net/ieee802154/6lowpan/core.c | 8 -- net/l2tp/l2tp_eth.c | 1 - net/netrom/af_netrom.c | 23 ---- net/rose/af_rose.c | 23 ---- net/sched/sch_generic.c | 17 +-- 25 files changed, 63 insertions(+), 356 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 21d8fcc83c9c..ac1b09b56c77 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4769,7 +4769,6 @@ static int bond_init(struct net_device *bond_dev) return -ENOMEM; bond->nest_level = SINGLE_DEPTH_NESTING; - netdev_lockdep_set_classes(bond_dev); list_add_tail(&bond->bond_list, &bn->dev_list); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 1eef446036d6..79d72c88bbef 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -299,22 +299,6 @@ static void nfp_repr_clean(struct nfp_repr *repr) nfp_port_free(repr->port); } -static struct lock_class_key nfp_repr_netdev_xmit_lock_key; -static struct lock_class_key nfp_repr_netdev_addr_lock_key; - -static void nfp_repr_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &nfp_repr_netdev_xmit_lock_key); -} - -static void nfp_repr_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &nfp_repr_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, nfp_repr_set_lockdep_class_one, NULL); -} - int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, u32 cmsg_port_id, struct nfp_port *port, struct net_device *pf_netdev) @@ -324,8 +308,6 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, u32 repr_cap = nn->tlv_caps.repr_cap; int err; - nfp_repr_set_lockdep_class(netdev); - repr->port = port; repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL); if (!repr->dst) diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index fbec711ff514..fbea6f232819 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -107,27 +107,6 @@ struct bpqdev { static LIST_HEAD(bpq_devices); -/* - * bpqether network devices are paired with ethernet devices below them, so - * form a special "super class" of normal ethernet devices; split their locks - * off into a separate class since they always nest. - */ -static struct lock_class_key bpq_netdev_xmit_lock_key; -static struct lock_class_key bpq_netdev_addr_lock_key; - -static void bpq_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &bpq_netdev_xmit_lock_key); -} - -static void bpq_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &bpq_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, bpq_set_lockdep_class_one, NULL); -} - /* ------------------------------------------------------------------------ */ @@ -498,7 +477,6 @@ static int bpq_new_device(struct net_device *edev) err = register_netdevice(ndev); if (err) goto error; - bpq_set_lockdep_class(ndev); /* List protected by RTNL */ list_add_rcu(&bpq->bpq_list, &bpq_devices); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 39dddcd8b3cb..fd4fff57fd6e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2335,8 +2335,6 @@ static int netvsc_probe(struct hv_device *dev, NETIF_F_HW_VLAN_CTAG_RX; net->vlan_features = net->features; - netdev_lockdep_set_classes(net); - /* MTU range: 68 - 1500 or 65521 */ net->min_mtu = NETVSC_MTU_MIN; if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 887bbba4631e..ba3dfac1d904 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -131,8 +131,6 @@ static int ipvlan_init(struct net_device *dev) dev->gso_max_segs = phy_dev->gso_max_segs; dev->hard_header_len = phy_dev->hard_header_len; - netdev_lockdep_set_classes(dev); - ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats); if (!ipvlan->pcpu_stats) return -ENOMEM; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index cb7637364b40..e2a3d1d5795f 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2750,7 +2750,6 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, #define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) -static struct lock_class_key macsec_netdev_addr_lock_key; static int macsec_dev_init(struct net_device *dev) { @@ -3264,10 +3263,6 @@ static int macsec_newlink(struct net *net, struct net_device *dev, dev_hold(real_dev); macsec->nest_level = dev_get_nest_level(real_dev) + 1; - netdev_lockdep_set_classes(dev); - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &macsec_netdev_addr_lock_key, - macsec_get_nest_level(dev)); err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 940192c057b6..0354e9be2ca5 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -852,8 +852,6 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) * "super class" of normal network devices; split their locks off into a * separate class since they always nest. */ -static struct lock_class_key macvlan_netdev_addr_lock_key; - #define ALWAYS_ON_OFFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL) @@ -874,14 +872,6 @@ static int macvlan_get_nest_level(struct net_device *dev) return ((struct macvlan_dev *)netdev_priv(dev))->nest_level; } -static void macvlan_set_lockdep_class(struct net_device *dev) -{ - netdev_lockdep_set_classes(dev); - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &macvlan_netdev_addr_lock_key, - macvlan_get_nest_level(dev)); -} - static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -900,8 +890,6 @@ static int macvlan_init(struct net_device *dev) dev->gso_max_segs = lowerdev->gso_max_segs; dev->hard_header_len = lowerdev->hard_header_len; - macvlan_set_lockdep_class(dev); - vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 9a1b006904a7..61824bbb5588 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1324,8 +1324,6 @@ static int ppp_dev_init(struct net_device *dev) { struct ppp *ppp; - netdev_lockdep_set_classes(dev); - ppp = netdev_priv(dev); /* Let the netdevice take a reference on the ppp file. This ensures * that ppp_destroy_interface() won't run before the device gets diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index e8089def5a46..6cea83b48cad 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1642,8 +1642,6 @@ static int team_init(struct net_device *dev) goto err_options_register; netif_carrier_off(dev); - netdev_lockdep_set_classes(dev); - return 0; err_options_register: diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index ee52bde058df..b8228f50bc94 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -865,7 +865,6 @@ static int vrf_dev_init(struct net_device *dev) /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; - netdev_lockdep_set_classes(dev); return 0; out_rth: diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c index 158a3d762e55..e323e9a5999f 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_hw.c +++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c @@ -3041,30 +3041,6 @@ static void prism2_clear_set_tim_queue(local_info_t *local) } } - -/* - * HostAP uses two layers of net devices, where the inner - * layer gets called all the time from the outer layer. - * This is a natural nesting, which needs a split lock type. - */ -static struct lock_class_key hostap_netdev_xmit_lock_key; -static struct lock_class_key hostap_netdev_addr_lock_key; - -static void prism2_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, - &hostap_netdev_xmit_lock_key); -} - -static void prism2_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, - &hostap_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, prism2_set_lockdep_class_one, NULL); -} - static struct net_device * prism2_init_local_data(struct prism2_helper_functions *funcs, int card_idx, struct device *sdev) @@ -3223,7 +3199,6 @@ while (0) if (ret >= 0) ret = register_netdevice(dev); - prism2_set_lockdep_class(dev); rtnl_unlock(); if (ret < 0) { printk(KERN_WARNING "%s: register netdevice failed!\n", diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 38c5909e1c35..c93df7cf187b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -925,6 +925,7 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1760,9 +1761,13 @@ enum netdev_priv_flags { * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. - * - * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock - * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount + * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock + spinlock + * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount + * @qdisc_xmit_lock_key: lockdep class annotating + * netdev_queue->_xmit_lock spinlock + * @addr_list_lock_key: lockdep class annotating + * net_device->addr_list_lock spinlock * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the @@ -2049,8 +2054,10 @@ struct net_device { #endif struct phy_device *phydev; struct sfp_bus *sfp_bus; - struct lock_class_key *qdisc_tx_busylock; - struct lock_class_key *qdisc_running_key; + struct lock_class_key qdisc_tx_busylock_key; + struct lock_class_key qdisc_running_key; + struct lock_class_key qdisc_xmit_lock_key; + struct lock_class_key addr_list_lock_key; bool proto_down; unsigned wol_enabled:1; }; @@ -2128,23 +2135,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } -#define netdev_lockdep_set_classes(dev) \ -{ \ - static struct lock_class_key qdisc_tx_busylock_key; \ - static struct lock_class_key qdisc_running_key; \ - static struct lock_class_key qdisc_xmit_lock_key; \ - static struct lock_class_key dev_addr_list_lock_key; \ - unsigned int i; \ - \ - (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ - (dev)->qdisc_running_key = &qdisc_running_key; \ - lockdep_set_class(&(dev)->addr_list_lock, \ - &dev_addr_list_lock_key); \ - for (i = 0; i < (dev)->num_tx_queues; i++) \ - lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ - &qdisc_xmit_lock_key); \ -} - u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, @@ -3143,6 +3133,7 @@ static inline void netif_stop_queue(struct net_device *dev) } void netif_tx_stop_all_queues(struct net_device *dev); +void netdev_update_lockdep_key(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 93eadf179123..6e6f26bf6e73 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -489,31 +489,6 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } -/* - * vlan network devices have devices nesting below it, and are a special - * "super class" of normal network devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key vlan_netdev_xmit_lock_key; -static struct lock_class_key vlan_netdev_addr_lock_key; - -static void vlan_dev_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_subclass) -{ - lockdep_set_class_and_subclass(&txq->_xmit_lock, - &vlan_netdev_xmit_lock_key, - *(int *)_subclass); -} - -static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) -{ - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &vlan_netdev_addr_lock_key, - subclass); - netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass); -} - static int vlan_dev_get_lock_subclass(struct net_device *dev) { return vlan_dev_priv(dev)->nest_level; @@ -609,8 +584,6 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev)); - vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) return -ENOMEM; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 9cbed6f5a85a..5ee8e9a100f9 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -740,36 +740,6 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto, return 0; } -/* batman-adv network devices have devices nesting below it and are a special - * "super class" of normal network devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key batadv_netdev_xmit_lock_key; -static struct lock_class_key batadv_netdev_addr_lock_key; - -/** - * batadv_set_lockdep_class_one() - Set lockdep class for a single tx queue - * @dev: device which owns the tx queue - * @txq: tx queue to modify - * @_unused: always NULL - */ -static void batadv_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &batadv_netdev_xmit_lock_key); -} - -/** - * batadv_set_lockdep_class() - Set txq and addr_list lockdep class - * @dev: network device to modify - */ -static void batadv_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &batadv_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL); -} - /** * batadv_softif_init_late() - late stage initialization of soft interface * @dev: registered network device to modify @@ -783,8 +753,6 @@ static int batadv_softif_init_late(struct net_device *dev) int ret; size_t cnt_len = sizeof(u64) * BATADV_CNT_NUM; - batadv_set_lockdep_class(dev); - bat_priv = netdev_priv(dev); bat_priv->soft_iface = dev; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index bb55d92691b0..4febc82a7c76 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -571,15 +571,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) return err < 0 ? NET_XMIT_DROP : err; } -static int bt_dev_init(struct net_device *dev) -{ - netdev_lockdep_set_classes(dev); - - return 0; -} - static const struct net_device_ops netdev_ops = { - .ndo_init = bt_dev_init, .ndo_start_xmit = bt_xmit, }; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 681b72862c16..e804a3016902 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -24,8 +24,6 @@ const struct nf_br_ops __rcu *nf_br_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_br_ops); -static struct lock_class_key bridge_netdev_addr_lock_key; - /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -108,11 +106,6 @@ out: return NETDEV_TX_OK; } -static void br_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); -} - static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -150,7 +143,6 @@ static int br_dev_init(struct net_device *dev) br_mdb_hash_fini(br); br_fdb_hash_fini(br); } - br_set_lockdep_class(dev); return err; } diff --git a/net/core/dev.c b/net/core/dev.c index ab0edfc4a422..5722a81b6edd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -277,88 +277,6 @@ static RAW_NOTIFIER_HEAD(netdev_chain); DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data); -#ifdef CONFIG_LOCKDEP -/* - * register_netdevice() inits txq->_xmit_lock and sets lockdep class - * according to dev->type - */ -static const unsigned short netdev_lock_type[] = { - ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, - ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, - ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, - ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, - ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, - ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, - ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, - ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, - ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, - ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, - ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, - ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, - ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, - ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, - ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; - -static const char *const netdev_lock_name[] = { - "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", - "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", - "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", - "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", - "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", - "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", - "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", - "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", - "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", - "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", - "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", - "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; - -static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; -static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; - -static inline unsigned short netdev_lock_pos(unsigned short dev_type) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) - if (netdev_lock_type[i] == dev_type) - return i; - /* the last key is used by default */ - return ARRAY_SIZE(netdev_lock_type) - 1; -} - -static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, - unsigned short dev_type) -{ - int i; - - i = netdev_lock_pos(dev_type); - lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], - netdev_lock_name[i]); -} - -static inline void netdev_set_addr_lockdep_class(struct net_device *dev) -{ - int i; - - i = netdev_lock_pos(dev->type); - lockdep_set_class_and_name(&dev->addr_list_lock, - &netdev_addr_lock_key[i], - netdev_lock_name[i]); -} -#else -static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, - unsigned short dev_type) -{ -} -static inline void netdev_set_addr_lockdep_class(struct net_device *dev) -{ -} -#endif - /******************************************************************************* * * Protocol management and registration routines @@ -8799,7 +8717,7 @@ static void netdev_init_one_queue(struct net_device *dev, { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; @@ -8846,6 +8764,43 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); +static void netdev_register_lockdep_key(struct net_device *dev) +{ + lockdep_register_key(&dev->qdisc_tx_busylock_key); + lockdep_register_key(&dev->qdisc_running_key); + lockdep_register_key(&dev->qdisc_xmit_lock_key); + lockdep_register_key(&dev->addr_list_lock_key); +} + +static void netdev_unregister_lockdep_key(struct net_device *dev) +{ + lockdep_unregister_key(&dev->qdisc_tx_busylock_key); + lockdep_unregister_key(&dev->qdisc_running_key); + lockdep_unregister_key(&dev->qdisc_xmit_lock_key); + lockdep_unregister_key(&dev->addr_list_lock_key); +} + +void netdev_update_lockdep_key(struct net_device *dev) +{ + struct netdev_queue *queue; + int i; + + lockdep_unregister_key(&dev->qdisc_xmit_lock_key); + lockdep_unregister_key(&dev->addr_list_lock_key); + + lockdep_register_key(&dev->qdisc_xmit_lock_key); + lockdep_register_key(&dev->addr_list_lock_key); + + lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); + for (i = 0; i < dev->num_tx_queues; i++) { + queue = netdev_get_tx_queue(dev, i); + + lockdep_set_class(&queue->_xmit_lock, + &dev->qdisc_xmit_lock_key); + } +} +EXPORT_SYMBOL(netdev_update_lockdep_key); + /** * register_netdevice - register a network device * @dev: device to register @@ -8880,7 +8835,7 @@ int register_netdevice(struct net_device *dev) BUG_ON(!net); spin_lock_init(&dev->addr_list_lock); - netdev_set_addr_lockdep_class(dev); + lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) @@ -9390,6 +9345,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); + netdev_register_lockdep_key(dev); + dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; dev->upper_level = 1; @@ -9474,6 +9431,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; + netdev_unregister_lockdep_key(dev); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1ee6460f8275..13493aae4e6c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2355,6 +2355,7 @@ static int do_set_master(struct net_device *dev, int ifindex, err = ops->ndo_del_slave(upper_dev, dev); if (err) return err; + netdev_update_lockdep_key(dev); } else { return -EOPNOTSUPP; } diff --git a/net/dsa/master.c b/net/dsa/master.c index a8e52c9967f4..3255dfc97f86 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -310,8 +310,6 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } -static struct lock_class_key dsa_master_addr_list_lock_key; - int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -325,9 +323,6 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; - lockdep_set_class(&dev->addr_list_lock, - &dsa_master_addr_list_lock_key); - ret = dsa_master_ethtool_setup(dev); if (ret) return ret; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 75d58229a4bd..028e65f4b5ba 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1341,15 +1341,6 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } -static struct lock_class_key dsa_slave_netdev_xmit_lock_key; -static void dsa_slave_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, - &dsa_slave_netdev_xmit_lock_key); -} - int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); @@ -1433,9 +1424,6 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->max_mtu = ETH_MAX_MTU; SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); - netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, - NULL); - SET_NETDEV_DEV(slave_dev, port->ds->dev); slave_dev->dev.of_node = port->dn; slave_dev->vlan_features = master->vlan_features; diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 3297e7fa9945..c0b107cdd715 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -58,13 +58,6 @@ static const struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; -static int lowpan_dev_init(struct net_device *ldev) -{ - netdev_lockdep_set_classes(ldev); - - return 0; -} - static int lowpan_open(struct net_device *dev) { if (!open_count) @@ -96,7 +89,6 @@ static int lowpan_get_iflink(const struct net_device *dev) } static const struct net_device_ops lowpan_netdev_ops = { - .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index fd5ac2788e45..d3b520b9b2c9 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -56,7 +56,6 @@ static int l2tp_eth_dev_init(struct net_device *dev) { eth_hw_addr_random(dev); eth_broadcast_addr(dev->broadcast); - netdev_lockdep_set_classes(dev); return 0; } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index c4f54ad2b98a..58d5373c513c 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -63,28 +63,6 @@ static DEFINE_SPINLOCK(nr_list_lock); static const struct proto_ops nr_proto_ops; -/* - * NETROM network devices are virtual network devices encapsulating NETROM - * frames into AX.25 which will be sent through an AX.25 device, so form a - * special "super class" of normal net devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key nr_netdev_xmit_lock_key; -static struct lock_class_key nr_netdev_addr_lock_key; - -static void nr_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &nr_netdev_xmit_lock_key); -} - -static void nr_set_lockdep_key(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL); -} - /* * Socket removal during an interrupt is now safe. */ @@ -1414,7 +1392,6 @@ static int __init nr_proto_init(void) free_netdev(dev); goto fail; } - nr_set_lockdep_key(dev); dev_nr[i] = dev; } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index f0e9ccf472a9..6a0df7c8a939 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -64,28 +64,6 @@ static const struct proto_ops rose_proto_ops; ax25_address rose_callsign; -/* - * ROSE network devices are virtual network devices encapsulating ROSE - * frames into AX.25 which will be sent through an AX.25 device, so form a - * special "super class" of normal net devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key rose_netdev_xmit_lock_key; -static struct lock_class_key rose_netdev_addr_lock_key; - -static void rose_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &rose_netdev_xmit_lock_key); -} - -static void rose_set_lockdep_key(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &rose_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL); -} - /* * Convert a ROSE address into text. */ @@ -1533,7 +1511,6 @@ static int __init rose_proto_init(void) free_netdev(dev); goto fail; } - rose_set_lockdep_key(dev); dev_rose[i] = dev; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 17bd8f539bc7..b2d34c49cbe6 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -799,9 +799,6 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { }; EXPORT_SYMBOL(pfifo_fast_ops); -static struct lock_class_key qdisc_tx_busylock; -static struct lock_class_key qdisc_running_key; - struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack) @@ -854,17 +851,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, } spin_lock_init(&sch->busylock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - seqcount_init(&sch->running); - lockdep_set_class(&sch->running, - dev->qdisc_running_key ?: &qdisc_running_key); sch->ops = ops; sch->flags = ops->static_flags; @@ -875,6 +864,12 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, dev_hold(dev); refcount_set(&sch->refcnt, 1); + if (sch != &noop_qdisc) { + lockdep_set_class(&sch->busylock, &dev->qdisc_tx_busylock_key); + lockdep_set_class(&sch->seqlock, &dev->qdisc_tx_busylock_key); + lockdep_set_class(&sch->running, &dev->qdisc_running_key); + } + return sch; errout1: kfree(p); -- cgit v1.2.3 From 32b6d34fedc2229cdf6a047fdbc0704085441915 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:56 +0000 Subject: net: core: add ignore flag to netdev_adjacent structure In order to link an adjacent node, netdev_upper_dev_link() is used and in order to unlink an adjacent node, netdev_upper_dev_unlink() is used. unlink operation does not fail, but link operation can fail. In order to exchange adjacent nodes, we should unlink an old adjacent node first. then, link a new adjacent node. If link operation is failed, we should link an old adjacent node again. But this link operation can fail too. It eventually breaks the adjacent link relationship. This patch adds an ignore flag into the netdev_adjacent structure. If this flag is set, netdev_upper_dev_link() ignores an old adjacent node for a moment. This patch also adds new functions for other modules. netdev_adjacent_change_prepare() netdev_adjacent_change_commit() netdev_adjacent_change_abort() netdev_adjacent_change_prepare() inserts new device into adjacent list but new device is not allowed to use immediately. If netdev_adjacent_change_prepare() fails, it internally rollbacks adjacent list so that we don't need any other action. netdev_adjacent_change_commit() deletes old device in the adjacent list and allows new device to use. netdev_adjacent_change_abort() rollbacks adjacent list. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++ net/core/dev.c | 230 +++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 219 insertions(+), 21 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c93df7cf187b..6c6490e15cd4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4324,6 +4324,16 @@ int netdev_master_upper_dev_link(struct net_device *dev, struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); +int netdev_adjacent_change_prepare(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev, + struct netlink_ext_ack *extack); +void netdev_adjacent_change_commit(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev); +void netdev_adjacent_change_abort(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); diff --git a/net/core/dev.c b/net/core/dev.c index 5722a81b6edd..092c094038b6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6408,6 +6408,9 @@ struct netdev_adjacent { /* upper master flag, there can only be one master device per list */ bool master; + /* lookup ignore flag */ + bool ignore; + /* counter for the number of times this device was added to us */ u16 ref_nr; @@ -6430,7 +6433,7 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, return NULL; } -static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data) +static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) { struct net_device *dev = data; @@ -6451,7 +6454,7 @@ bool netdev_has_upper_dev(struct net_device *dev, { ASSERT_RTNL(); - return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -6469,7 +6472,7 @@ EXPORT_SYMBOL(netdev_has_upper_dev); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { - return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); @@ -6513,6 +6516,22 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get); +static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) +{ + struct netdev_adjacent *upper; + + ASSERT_RTNL(); + + if (list_empty(&dev->adj_list.upper)) + return NULL; + + upper = list_first_entry(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (likely(upper->master) && !upper->ignore) + return upper->dev; + return NULL; +} + /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device @@ -6563,8 +6582,9 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); -static struct net_device *netdev_next_upper_dev(struct net_device *dev, - struct list_head **iter) +static struct net_device *__netdev_next_upper_dev(struct net_device *dev, + struct list_head **iter, + bool *ignore) { struct netdev_adjacent *upper; @@ -6574,6 +6594,7 @@ static struct net_device *netdev_next_upper_dev(struct net_device *dev, return NULL; *iter = &upper->list; + *ignore = upper->ignore; return upper->dev; } @@ -6595,14 +6616,15 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, return upper->dev; } -static int netdev_walk_all_upper_dev(struct net_device *dev, - int (*fn)(struct net_device *dev, - void *data), - void *data) +static int __netdev_walk_all_upper_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; + bool ignore; now = dev; iter = &dev->adj_list.upper; @@ -6616,9 +6638,11 @@ static int netdev_walk_all_upper_dev(struct net_device *dev, next = NULL; while (1) { - udev = netdev_next_upper_dev(now, &iter); + udev = __netdev_next_upper_dev(now, &iter, &ignore); if (!udev) break; + if (ignore) + continue; next = udev; niter = &udev->adj_list.upper; @@ -6688,6 +6712,15 @@ int netdev_walk_all_upper_dev_rcu(struct net_device *dev, } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); +static bool __netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) +{ + ASSERT_RTNL(); + + return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, + upper_dev); +} + /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list @@ -6784,6 +6817,23 @@ static struct net_device *netdev_next_lower_dev(struct net_device *dev, return lower->dev; } +static struct net_device *__netdev_next_lower_dev(struct net_device *dev, + struct list_head **iter, + bool *ignore) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + *ignore = lower->ignore; + + return lower->dev; +} + int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), @@ -6831,6 +6881,55 @@ int netdev_walk_all_lower_dev(struct net_device *dev, } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); +static int __netdev_walk_all_lower_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + bool ignore; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = __netdev_next_lower_dev(now, &iter, &ignore); + if (!ldev) + break; + if (ignore) + continue; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { @@ -6850,11 +6949,14 @@ static u8 __netdev_upper_depth(struct net_device *dev) struct net_device *udev; struct list_head *iter; u8 max_depth = 0; + bool ignore; for (iter = &dev->adj_list.upper, - udev = netdev_next_upper_dev(dev, &iter); + udev = __netdev_next_upper_dev(dev, &iter, &ignore); udev; - udev = netdev_next_upper_dev(dev, &iter)) { + udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { + if (ignore) + continue; if (max_depth < udev->upper_level) max_depth = udev->upper_level; } @@ -6867,11 +6969,14 @@ static u8 __netdev_lower_depth(struct net_device *dev) struct net_device *ldev; struct list_head *iter; u8 max_depth = 0; + bool ignore; for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev(dev, &iter); + ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; - ldev = netdev_next_lower_dev(dev, &iter)) { + ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { + if (ignore) + continue; if (max_depth < ldev->lower_level) max_depth = ldev->lower_level; } @@ -7035,6 +7140,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->master = master; adj->ref_nr = 1; adj->private = private; + adj->ignore = false; dev_hold(adj_dev); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", @@ -7185,17 +7291,17 @@ static int __netdev_upper_dev_link(struct net_device *dev, return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ - if (netdev_has_upper_dev(upper_dev, dev)) + if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) return -EMLINK; if (!master) { - if (netdev_has_upper_dev(dev, upper_dev)) + if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { - master_dev = netdev_master_upper_dev_get(dev); + master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } @@ -7218,10 +7324,11 @@ static int __netdev_upper_dev_link(struct net_device *dev, goto rollback; __netdev_update_upper_level(dev, NULL); - netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, NULL); - netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL); + __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, + NULL); return 0; @@ -7307,13 +7414,94 @@ void netdev_upper_dev_unlink(struct net_device *dev, &changeupper_info.info); __netdev_update_upper_level(dev, NULL); - netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, NULL); - netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL); + __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, + NULL); } EXPORT_SYMBOL(netdev_upper_dev_unlink); +static void __netdev_adjacent_dev_set(struct net_device *upper_dev, + struct net_device *lower_dev, + bool val) +{ + struct netdev_adjacent *adj; + + adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); + if (adj) + adj->ignore = val; + + adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); + if (adj) + adj->ignore = val; +} + +static void netdev_adjacent_dev_disable(struct net_device *upper_dev, + struct net_device *lower_dev) +{ + __netdev_adjacent_dev_set(upper_dev, lower_dev, true); +} + +static void netdev_adjacent_dev_enable(struct net_device *upper_dev, + struct net_device *lower_dev) +{ + __netdev_adjacent_dev_set(upper_dev, lower_dev, false); +} + +int netdev_adjacent_change_prepare(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev, + struct netlink_ext_ack *extack) +{ + int err; + + if (!new_dev) + return 0; + + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_disable(dev, old_dev); + + err = netdev_upper_dev_link(new_dev, dev, extack); + if (err) { + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_enable(dev, old_dev); + return err; + } + + return 0; +} +EXPORT_SYMBOL(netdev_adjacent_change_prepare); + +void netdev_adjacent_change_commit(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev) +{ + if (!new_dev || !old_dev) + return; + + if (new_dev == old_dev) + return; + + netdev_adjacent_dev_enable(dev, old_dev); + netdev_upper_dev_unlink(old_dev, dev); +} +EXPORT_SYMBOL(netdev_adjacent_change_commit); + +void netdev_adjacent_change_abort(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev) +{ + if (!new_dev) + return; + + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_enable(dev, old_dev); + + netdev_upper_dev_unlink(new_dev, dev); +} +EXPORT_SYMBOL(netdev_adjacent_change_abort); + /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device -- cgit v1.2.3 From f3b0a18bb6cb07a9abb75e21b1f08eeaefa78e81 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 21 Oct 2019 18:47:58 +0000 Subject: net: remove unnecessary variables and callback This patch removes variables and callback these are related to the nested device structure. devices that can be nested have their own nest_level variable that represents the depth of nested devices. In the previous patch, new {lower/upper}_level variables are added and they replace old private nest_level variable. So, this patch removes all 'nest_level' variables. In order to avoid lockdep warning, ->ndo_get_lock_subclass() was added to get lockdep subclass value, which is actually lower nested depth value. But now, they use the dynamic lockdep key to avoid lockdep warning instead of the subclass. So, this patch removes ->ndo_get_lock_subclass() callback. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- drivers/net/bonding/bond_alb.c | 2 +- drivers/net/bonding/bond_main.c | 15 --------------- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- drivers/net/macsec.c | 9 --------- drivers/net/macvlan.c | 7 ------- include/linux/if_macvlan.h | 1 - include/linux/if_vlan.h | 11 ----------- include/linux/netdevice.h | 12 ------------ include/net/bonding.h | 1 - net/8021q/vlan.c | 1 - net/8021q/vlan_dev.c | 6 ------ net/core/dev.c | 19 ------------------- net/core/dev_addr_lists.c | 12 ++++++------ net/smc/smc_core.c | 2 +- net/smc/smc_pnet.c | 2 +- 15 files changed, 10 insertions(+), 92 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 8c79bad2a9a5..4f2e6910c623 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -952,7 +952,7 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data) struct bond_vlan_tag *tags; if (is_vlan_dev(upper) && - bond->nest_level == vlan_get_encap_level(upper) - 1) { + bond->dev->lower_level == upper->lower_level - 1) { if (upper->addr_assign_type == NET_ADDR_STOLEN) { alb_send_lp_vid(slave, mac_addr, vlan_dev_vlan_proto(upper), diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 6a6273590288..a48950b81434 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1733,8 +1733,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_upper_unlink; } - bond->nest_level = dev_get_nest_level(bond_dev) + 1; - /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ @@ -1957,9 +1955,6 @@ static int __bond_release_one(struct net_device *bond_dev, if (!bond_has_slaves(bond)) { bond_set_carrier(bond); eth_hw_addr_random(bond_dev); - bond->nest_level = SINGLE_DEPTH_NESTING; - } else { - bond->nest_level = dev_get_nest_level(bond_dev) + 1; } unblock_netpoll_tx(); @@ -3444,13 +3439,6 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } -static int bond_get_nest_level(struct net_device *bond_dev) -{ - struct bonding *bond = netdev_priv(bond_dev); - - return bond->nest_level; -} - static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -4270,7 +4258,6 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, - .ndo_get_lock_subclass = bond_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, @@ -4769,8 +4756,6 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; - bond->nest_level = SINGLE_DEPTH_NESTING; - spin_lock_init(&bond->mode_lock); spin_lock_init(&bond->stats_lock); lockdep_register_key(&bond->stats_lock_key); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3e78a727f3e6..c4c59d2e676e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3160,7 +3160,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr, u32 *action) { - int nest_level = vlan_get_encap_level(attr->parse_attr->filter_dev); + int nest_level = attr->parse_attr->filter_dev->lower_level; struct flow_action_entry vlan_act = { .id = FLOW_ACTION_VLAN_POP, }; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 9e97b66b26d3..afd8b2a08245 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -267,7 +267,6 @@ struct macsec_dev { struct pcpu_secy_stats __percpu *stats; struct list_head secys; struct gro_cells gro_cells; - unsigned int nest_level; }; /** @@ -2957,11 +2956,6 @@ static int macsec_get_iflink(const struct net_device *dev) return macsec_priv(dev)->real_dev->ifindex; } -static int macsec_get_nest_level(struct net_device *dev) -{ - return macsec_priv(dev)->nest_level; -} - static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, @@ -2975,7 +2969,6 @@ static const struct net_device_ops macsec_netdev_ops = { .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, - .ndo_get_lock_subclass = macsec_get_nest_level, }; static const struct device_type macsec_type = { @@ -3258,8 +3251,6 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (err < 0) return err; - macsec->nest_level = dev_get_nest_level(real_dev) + 1; - err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) goto unregister; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 0354e9be2ca5..34fc59bd1e20 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -867,11 +867,6 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) -static int macvlan_get_nest_level(struct net_device *dev) -{ - return ((struct macvlan_dev *)netdev_priv(dev))->nest_level; -} - static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -1149,7 +1144,6 @@ static const struct net_device_ops macvlan_netdev_ops = { .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, - .ndo_get_lock_subclass = macvlan_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macvlan_dev_poll_controller, .ndo_netpoll_setup = macvlan_dev_netpoll_setup, @@ -1433,7 +1427,6 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; - vlan->nest_level = dev_get_nest_level(lowerdev) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 2e55e4cdbd8a..a367ead4bf4b 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -29,7 +29,6 @@ struct macvlan_dev { netdev_features_t set_features; enum macvlan_mode mode; u16 flags; - int nest_level; unsigned int macaddr_count; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 244278d5c222..b05e855f1ddd 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -182,7 +182,6 @@ struct vlan_dev_priv { #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif - unsigned int nest_level; }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) @@ -221,11 +220,6 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, extern bool vlan_uses_dev(const struct net_device *dev); -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG_ON(!is_vlan_dev(dev)); - return vlan_dev_priv(dev)->nest_level; -} #else static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, @@ -295,11 +289,6 @@ static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG(); - return 0; -} #endif /** diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6c6490e15cd4..c20f190b4c18 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1422,7 +1422,6 @@ struct net_device_ops { void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); - int (*ndo_get_lock_subclass)(struct net_device *dev); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); @@ -4051,16 +4050,6 @@ static inline void netif_addr_lock(struct net_device *dev) spin_lock(&dev->addr_list_lock); } -static inline void netif_addr_lock_nested(struct net_device *dev) -{ - int subclass = SINGLE_DEPTH_NESTING; - - if (dev->netdev_ops->ndo_get_lock_subclass) - subclass = dev->netdev_ops->ndo_get_lock_subclass(dev); - - spin_lock_nested(&dev->addr_list_lock, subclass); -} - static inline void netif_addr_lock_bh(struct net_device *dev) { spin_lock_bh(&dev->addr_list_lock); @@ -4345,7 +4334,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); int skb_crc32c_csum_help(struct sk_buff *skb); int skb_csum_hwoffload_help(struct sk_buff *skb, diff --git a/include/net/bonding.h b/include/net/bonding.h index 334909feb2bb..1afc125014da 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -203,7 +203,6 @@ struct bonding { struct slave __rcu *primary_slave; struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */ bool force_primary; - u32 nest_level; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 54728d2eda18..d4bcfd8f95bf 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -172,7 +172,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 6e6f26bf6e73..e5bff5cc6f97 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -489,11 +489,6 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } -static int vlan_dev_get_lock_subclass(struct net_device *dev) -{ - return vlan_dev_priv(dev)->nest_level; -} - static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .parse = eth_header_parse, @@ -785,7 +780,6 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, - .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, .ndo_get_iflink = vlan_dev_get_iflink, }; diff --git a/net/core/dev.c b/net/core/dev.c index 092c094038b6..1482e2ef2d25 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7615,25 +7615,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(struct net_device *dev) -{ - struct net_device *lower = NULL; - struct list_head *iter; - int max_nest = -1; - int nest; - - ASSERT_RTNL(); - - netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower); - if (max_nest < nest) - max_nest = nest; - } - - return max_nest + 1; -} -EXPORT_SYMBOL(dev_get_nest_level); - /** * netdev_lower_change - Dispatch event about lower device state change * @lower_dev: device diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 6393ba930097..2f949b5a1eb9 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 88556f0251ab..2ba97ff325a5 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -561,7 +561,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) } rtnl_lock(); - nest_lvl = dev_get_nest_level(ndev); + nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index bab2da8cf17a..2920b006f65c 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -718,7 +718,7 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) int i, nest_lvl; rtnl_lock(); - nest_lvl = dev_get_nest_level(ndev); + nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; -- cgit v1.2.3 From de7d5084d82794a8e83afb994fcb07f82da3cd7b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 16:27:14 -0800 Subject: net: provide dev_lstats_read() helper Many network drivers use hand-coded implementation of the same thing, let's factorize things so that u64_stats_t adoption is done once. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/loopback.c | 24 +++++++++++++++++------- include/linux/netdevice.h | 2 ++ 2 files changed, 19 insertions(+), 7 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 14545a8797a8..92336ac4c5e6 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -99,13 +99,13 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } -static void loopback_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) +void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes) { - u64 bytes = 0; - u64 packets = 0; int i; + *packets = 0; + *bytes = 0; + for_each_possible_cpu(i) { const struct pcpu_lstats *lb_stats; u64 tbytes, tpackets; @@ -114,12 +114,22 @@ static void loopback_get_stats64(struct net_device *dev, lb_stats = per_cpu_ptr(dev->lstats, i); do { start = u64_stats_fetch_begin_irq(&lb_stats->syncp); - tbytes = lb_stats->bytes; tpackets = lb_stats->packets; + tbytes = lb_stats->bytes; } while (u64_stats_fetch_retry_irq(&lb_stats->syncp, start)); - bytes += tbytes; - packets += tpackets; + *bytes += tbytes; + *packets += tpackets; } +} +EXPORT_SYMBOL(dev_lstats_read); + +static void loopback_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + u64 packets, bytes; + + dev_lstats_read(dev, &packets, &bytes); + stats->rx_packets = packets; stats->tx_packets = packets; stats->rx_bytes = bytes; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1f140a6b66df..75561992c31f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2401,6 +2401,8 @@ struct pcpu_lstats { struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); +void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ -- cgit v1.2.3 From dd5382a08157756510aa8d7269c662eccde775cb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 16:27:15 -0800 Subject: net: provide dev_lstats_add() helper Many network drivers need it and hand-coded the same function. In order to ease u64_stats_t adoption, it is time to factorize. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/loopback.c | 12 ++---------- include/linux/netdevice.h | 10 ++++++++++ 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 92336ac4c5e6..47ad2478b9f3 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -68,7 +68,6 @@ EXPORT_SYMBOL(blackhole_netdev); static netdev_tx_t loopback_xmit(struct sk_buff *skb, struct net_device *dev) { - struct pcpu_lstats *lb_stats; int len; skb_tx_timestamp(skb); @@ -85,16 +84,9 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, skb->protocol = eth_type_trans(skb, dev); - /* it's OK to use per_cpu_ptr() because BHs are off */ - lb_stats = this_cpu_ptr(dev->lstats); - len = skb->len; - if (likely(netif_rx(skb) == NET_RX_SUCCESS)) { - u64_stats_update_begin(&lb_stats->syncp); - lb_stats->bytes += len; - lb_stats->packets++; - u64_stats_update_end(&lb_stats->syncp); - } + if (likely(netif_rx(skb) == NET_RX_SUCCESS)) + dev_lstats_add(dev, len); return NETDEV_TX_OK; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 75561992c31f..461a36220cf4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2403,6 +2403,16 @@ struct pcpu_lstats { void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); +static inline void dev_lstats_add(struct net_device *dev, unsigned int len) +{ + struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); + + u64_stats_update_begin(&lstats->syncp); + lstats->bytes += len; + lstats->packets++; + u64_stats_update_end(&lstats->syncp); +} + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ -- cgit v1.2.3 From fd2f4737870eb866537fbbffa2b59414b9b0c0a2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 16:27:22 -0800 Subject: net: use u64_stats_t in struct pcpu_lstats In order to fix the data-race found by KCSAN, we can use the new u64_stats_t type and its accessors instead of plain u64 fields. This will still generate optimal code for both 32 and 64 bit platforms. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/loopback.c | 4 ++-- include/linux/netdevice.h | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 47ad2478b9f3..a1c77cc00416 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -106,8 +106,8 @@ void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes) lb_stats = per_cpu_ptr(dev->lstats, i); do { start = u64_stats_fetch_begin_irq(&lb_stats->syncp); - tpackets = lb_stats->packets; - tbytes = lb_stats->bytes; + tpackets = u64_stats_read(&lb_stats->packets); + tbytes = u64_stats_read(&lb_stats->bytes); } while (u64_stats_fetch_retry_irq(&lb_stats->syncp, start)); *bytes += tbytes; *packets += tpackets; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 461a36220cf4..f857f01234f7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2396,8 +2396,8 @@ struct pcpu_sw_netstats { } __aligned(4 * sizeof(u64)); struct pcpu_lstats { - u64 packets; - u64 bytes; + u64_stats_t packets; + u64_stats_t bytes; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); @@ -2408,8 +2408,8 @@ static inline void dev_lstats_add(struct net_device *dev, unsigned int len) struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&lstats->syncp); - lstats->bytes += len; - lstats->packets++; + u64_stats_add(&lstats->bytes, len); + u64_stats_inc(&lstats->packets); u64_stats_update_end(&lstats->syncp); } -- cgit v1.2.3 From c29f74e0df7a02b8303bcdce93a7c0132d62577a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 12 Nov 2019 00:29:56 +0100 Subject: netfilter: nf_flow_table: hardware offload support This patch adds the dataplane hardware offload to the flowtable infrastructure. Three new flags represent the hardware state of this flow: * FLOW_OFFLOAD_HW: This flow entry resides in the hardware. * FLOW_OFFLOAD_HW_DYING: This flow entry has been scheduled to be remove from hardware. This might be triggered by either packet path (via TCP RST/FIN packet) or via aging. * FLOW_OFFLOAD_HW_DEAD: This flow entry has been already removed from the hardware, the software garbage collector can remove it from the software flowtable. This patch supports for: * IPv4 only. * Aging via FLOW_CLS_STATS, no packet and byte counter synchronization at this stage. This patch also adds the action callback that specifies how to convert the flow entry into the flow_rule object that is passed to the driver. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/net/netfilter/nf_flow_table.h | 33 +- net/ipv4/netfilter/nf_flow_table_ipv4.c | 1 + net/ipv6/netfilter/nf_flow_table_ipv6.c | 1 + net/netfilter/Makefile | 3 +- net/netfilter/nf_flow_table_core.c | 33 +- net/netfilter/nf_flow_table_inet.c | 1 + net/netfilter/nf_flow_table_offload.c | 758 ++++++++++++++++++++++++++++++++ 8 files changed, 822 insertions(+), 9 deletions(-) create mode 100644 net/netfilter/nf_flow_table_offload.c (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f857f01234f7..9e6fb8524d91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -848,6 +848,7 @@ enum tc_setup_type { TC_SETUP_ROOT_QDISC, TC_SETUP_QDISC_GRED, TC_SETUP_QDISC_TAPRIO, + TC_SETUP_FT, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ece09d36c7a6..eea66de328d3 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -12,6 +12,9 @@ #include struct nf_flowtable; +struct nf_flow_rule; +struct flow_offload; +enum flow_offload_tuple_dir; struct nf_flowtable_type { struct list_head list; @@ -20,6 +23,10 @@ struct nf_flowtable_type { int (*setup)(struct nf_flowtable *ft, struct net_device *dev, enum flow_block_command cmd); + int (*action)(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; @@ -80,6 +87,9 @@ struct flow_offload_tuple_rhash { #define FLOW_OFFLOAD_DNAT 0x2 #define FLOW_OFFLOAD_DYING 0x4 #define FLOW_OFFLOAD_TEARDOWN 0x8 +#define FLOW_OFFLOAD_HW 0x10 +#define FLOW_OFFLOAD_HW_DYING 0x20 +#define FLOW_OFFLOAD_HW_DEAD 0x40 enum flow_offload_type { NF_FLOW_OFFLOAD_UNSPEC = 0, @@ -142,11 +152,22 @@ unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, #define MODULE_ALIAS_NF_FLOWTABLE(family) \ MODULE_ALIAS("nf-flowtable-" __stringify(family)) -static inline int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, - struct net_device *dev, - enum flow_block_command cmd) -{ - return 0; -} +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow); +void nf_flow_offload_del(struct nf_flowtable *flowtable, + struct flow_offload *flow); +void nf_flow_offload_stats(struct nf_flowtable *flowtable, + struct flow_offload *flow); + +void nf_flow_table_offload_flush(struct nf_flowtable *flowtable); +int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd); +int nf_flow_rule_route(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule); + +int nf_flow_table_offload_init(void); +void nf_flow_table_offload_exit(void); #endif /* _NF_FLOW_TABLE_H */ diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index f3befddb5fdd..168b72e18be0 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -10,6 +10,7 @@ static struct nf_flowtable_type flowtable_ipv4 = { .family = NFPROTO_IPV4, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, + .action = nf_flow_rule_route, .free = nf_flow_table_free, .hook = nf_flow_offload_ip_hook, .owner = THIS_MODULE, diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index 1c47f05eabd6..f069bc0dc056 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -11,6 +11,7 @@ static struct nf_flowtable_type flowtable_ipv6 = { .family = NFPROTO_IPV6, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, + .action = nf_flow_rule_route, .free = nf_flow_table_free, .hook = nf_flow_offload_ipv6_hook, .owner = THIS_MODULE, diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 4fc075b612fe..5e9b2eb24349 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -120,7 +120,8 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o # flow table infrastructure obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o -nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o +nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o \ + nf_flow_table_offload.o obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 139a5e074743..8468d2d02284 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -250,6 +250,9 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) return err; } + if (flow_table->flags & NF_FLOWTABLE_HW_OFFLOAD) + nf_flow_offload_add(flow_table, flow); + return 0; } EXPORT_SYMBOL_GPL(flow_offload_add); @@ -350,9 +353,20 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; + if (flow->flags & FLOW_OFFLOAD_HW) + nf_flow_offload_stats(flow_table, flow); + if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))) - flow_offload_del(flow_table, flow); + (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))) { + if (flow->flags & FLOW_OFFLOAD_HW) { + if (!(flow->flags & FLOW_OFFLOAD_HW_DYING)) + nf_flow_offload_del(flow_table, flow); + else if (flow->flags & FLOW_OFFLOAD_HW_DEAD) + flow_offload_del(flow_table, flow); + } else { + flow_offload_del(flow_table, flow); + } + } } static void nf_flow_offload_work_gc(struct work_struct *work) @@ -485,6 +499,7 @@ int nf_flow_table_init(struct nf_flowtable *flowtable) int err; INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc); + flow_block_init(&flowtable->flow_block); err = rhashtable_init(&flowtable->rhashtable, &nf_flow_offload_rhash_params); @@ -520,6 +535,7 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data) static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable, struct net_device *dev) { + nf_flow_table_offload_flush(flowtable); nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev); flush_delayed_work(&flowtable->gc_work); } @@ -547,5 +563,18 @@ void nf_flow_table_free(struct nf_flowtable *flow_table) } EXPORT_SYMBOL_GPL(nf_flow_table_free); +static int __init nf_flow_table_module_init(void) +{ + return nf_flow_table_offload_init(); +} + +static void __exit nf_flow_table_module_exit(void) +{ + nf_flow_table_offload_exit(); +} + +module_init(nf_flow_table_module_init); +module_exit(nf_flow_table_module_exit); + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso "); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 1e70fd504da3..bfb910b874ce 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -25,6 +25,7 @@ static struct nf_flowtable_type flowtable_inet = { .family = NFPROTO_INET, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, + .action = nf_flow_rule_route, .free = nf_flow_table_free, .hook = nf_flow_offload_inet_hook, .owner = THIS_MODULE, diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c new file mode 100644 index 000000000000..9be61f47303a --- /dev/null +++ b/net/netfilter/nf_flow_table_offload.c @@ -0,0 +1,758 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct work_struct nf_flow_offload_work; +static DEFINE_SPINLOCK(flow_offload_pending_list_lock); +static LIST_HEAD(flow_offload_pending_list); + +struct flow_offload_work { + struct list_head list; + enum flow_cls_command cmd; + int priority; + struct nf_flowtable *flowtable; + struct flow_offload *flow; +}; + +struct nf_flow_key { + struct flow_dissector_key_control control; + struct flow_dissector_key_basic basic; + union { + struct flow_dissector_key_ipv4_addrs ipv4; + }; + struct flow_dissector_key_tcp tcp; + struct flow_dissector_key_ports tp; +} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ + +struct nf_flow_match { + struct flow_dissector dissector; + struct nf_flow_key key; + struct nf_flow_key mask; +}; + +struct nf_flow_rule { + struct nf_flow_match match; + struct flow_rule *rule; +}; + +#define NF_FLOW_DISSECTOR(__match, __type, __field) \ + (__match)->dissector.offset[__type] = \ + offsetof(struct nf_flow_key, __field) + +static int nf_flow_rule_match(struct nf_flow_match *match, + const struct flow_offload_tuple *tuple) +{ + struct nf_flow_key *mask = &match->mask; + struct nf_flow_key *key = &match->key; + + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp); + + switch (tuple->l3proto) { + case AF_INET: + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + key->basic.n_proto = htons(ETH_P_IP); + key->ipv4.src = tuple->src_v4.s_addr; + mask->ipv4.src = 0xffffffff; + key->ipv4.dst = tuple->dst_v4.s_addr; + mask->ipv4.dst = 0xffffffff; + break; + default: + return -EOPNOTSUPP; + } + mask->basic.n_proto = 0xffff; + + switch (tuple->l4proto) { + case IPPROTO_TCP: + key->tcp.flags = 0; + mask->tcp.flags = TCP_FLAG_RST | TCP_FLAG_FIN; + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + break; + case IPPROTO_UDP: + break; + default: + return -EOPNOTSUPP; + } + + key->basic.ip_proto = tuple->l4proto; + mask->basic.ip_proto = 0xff; + + key->tp.src = tuple->src_port; + mask->tp.src = 0xffff; + key->tp.dst = tuple->dst_port; + mask->tp.dst = 0xffff; + + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS); + return 0; +} + +static void flow_offload_mangle(struct flow_action_entry *entry, + enum flow_action_mangle_base htype, + u32 offset, u8 *value, u8 *mask) +{ + entry->id = FLOW_ACTION_MANGLE; + entry->mangle.htype = htype; + entry->mangle.offset = offset; + memcpy(&entry->mangle.mask, mask, sizeof(u32)); + memcpy(&entry->mangle.val, value, sizeof(u32)); +} + +static int flow_offload_eth_src(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry0, + struct flow_action_entry *entry1) +{ + const struct flow_offload_tuple *tuple = &flow->tuplehash[!dir].tuple; + struct net_device *dev; + u32 mask, val; + u16 val16; + + dev = dev_get_by_index(net, tuple->iifidx); + if (!dev) + return -ENOENT; + + mask = ~0xffff0000; + memcpy(&val16, dev->dev_addr, 2); + val = val16 << 16; + flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, + (u8 *)&val, (u8 *)&mask); + + mask = ~0xffffffff; + memcpy(&val, dev->dev_addr + 2, 4); + flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, + (u8 *)&val, (u8 *)&mask); + dev_put(dev); + + return 0; +} + +static int flow_offload_eth_dst(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry0, + struct flow_action_entry *entry1) +{ + const struct flow_offload_tuple *tuple = &flow->tuplehash[dir].tuple; + struct neighbour *n; + u32 mask, val; + u16 val16; + + n = dst_neigh_lookup(tuple->dst_cache, &tuple->dst_v4); + if (!n) + return -ENOENT; + + mask = ~0xffffffff; + memcpy(&val, n->ha, 4); + flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0, + (u8 *)&val, (u8 *)&mask); + + mask = ~0x0000ffff; + memcpy(&val16, n->ha + 4, 2); + val = val16; + flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, + (u8 *)&val, (u8 *)&mask); + neigh_release(n); + + return 0; +} + +static void flow_offload_ipv4_snat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + u32 mask = ~htonl(0xffffffff); + __be32 addr; + u32 offset; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr; + offset = offsetof(struct iphdr, saddr); + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr; + offset = offsetof(struct iphdr, daddr); + break; + default: + return; + } + + flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, + (u8 *)&addr, (u8 *)&mask); +} + +static void flow_offload_ipv4_dnat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + u32 mask = ~htonl(0xffffffff); + __be32 addr; + u32 offset; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr; + offset = offsetof(struct iphdr, daddr); + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr; + offset = offsetof(struct iphdr, saddr); + break; + default: + return; + } + + flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, + (u8 *)&addr, (u8 *)&mask); +} + +static int flow_offload_l4proto(const struct flow_offload *flow) +{ + u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto; + u8 type = 0; + + switch (protonum) { + case IPPROTO_TCP: + type = FLOW_ACT_MANGLE_HDR_TYPE_TCP; + break; + case IPPROTO_UDP: + type = FLOW_ACT_MANGLE_HDR_TYPE_UDP; + break; + default: + break; + } + + return type; +} + +static void flow_offload_port_snat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + u32 mask = ~htonl(0xffff0000); + __be16 port; + u32 offset; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + offset = 0; /* offsetof(struct tcphdr, source); */ + break; + case FLOW_OFFLOAD_DIR_REPLY: + port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + offset = 0; /* offsetof(struct tcphdr, dest); */ + break; + default: + break; + } + + flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, + (u8 *)&port, (u8 *)&mask); +} + +static void flow_offload_port_dnat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + u32 mask = ~htonl(0xffff); + __be16 port; + u32 offset; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + offset = 0; /* offsetof(struct tcphdr, source); */ + break; + case FLOW_OFFLOAD_DIR_REPLY: + port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + offset = 0; /* offsetof(struct tcphdr, dest); */ + break; + default: + break; + } + + flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, + (u8 *)&port, (u8 *)&mask); +} + +static void flow_offload_ipv4_checksum(struct net *net, + const struct flow_offload *flow, + struct flow_action_entry *entry) +{ + u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto; + + entry->id = FLOW_ACTION_CSUM; + entry->csum_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR; + + switch (protonum) { + case IPPROTO_TCP: + entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_TCP; + break; + case IPPROTO_UDP: + entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_UDP; + break; + } +} + +static void flow_offload_redirect(const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + struct rtable *rt; + + rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache; + entry->id = FLOW_ACTION_REDIRECT; + entry->dev = rt->dst.dev; + dev_hold(rt->dst.dev); +} + +int nf_flow_rule_route(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) +{ + int i; + + if (flow_offload_eth_src(net, flow, dir, + &flow_rule->rule->action.entries[0], + &flow_rule->rule->action.entries[1]) < 0) + return -1; + + if (flow_offload_eth_dst(net, flow, dir, + &flow_rule->rule->action.entries[2], + &flow_rule->rule->action.entries[3]) < 0) + return -1; + + i = 4; + if (flow->flags & FLOW_OFFLOAD_SNAT) { + flow_offload_ipv4_snat(net, flow, dir, + &flow_rule->rule->action.entries[i++]); + flow_offload_port_snat(net, flow, dir, + &flow_rule->rule->action.entries[i++]); + } + if (flow->flags & FLOW_OFFLOAD_DNAT) { + flow_offload_ipv4_dnat(net, flow, dir, + &flow_rule->rule->action.entries[i++]); + flow_offload_port_dnat(net, flow, dir, + &flow_rule->rule->action.entries[i++]); + } + if (flow->flags & FLOW_OFFLOAD_SNAT || + flow->flags & FLOW_OFFLOAD_DNAT) + flow_offload_ipv4_checksum(net, flow, + &flow_rule->rule->action.entries[i++]); + + flow_offload_redirect(flow, dir, &flow_rule->rule->action.entries[i++]); + + return i; +} +EXPORT_SYMBOL_GPL(nf_flow_rule_route); + +static struct nf_flow_rule * +nf_flow_offload_rule_alloc(struct net *net, + const struct flow_offload_work *offload, + enum flow_offload_tuple_dir dir) +{ + const struct nf_flowtable *flowtable = offload->flowtable; + const struct flow_offload *flow = offload->flow; + const struct flow_offload_tuple *tuple; + struct nf_flow_rule *flow_rule; + int err = -ENOMEM, num_actions; + + flow_rule = kzalloc(sizeof(*flow_rule), GFP_KERNEL); + if (!flow_rule) + goto err_flow; + + flow_rule->rule = flow_rule_alloc(10); + if (!flow_rule->rule) + goto err_flow_rule; + + flow_rule->rule->match.dissector = &flow_rule->match.dissector; + flow_rule->rule->match.mask = &flow_rule->match.mask; + flow_rule->rule->match.key = &flow_rule->match.key; + + tuple = &flow->tuplehash[dir].tuple; + err = nf_flow_rule_match(&flow_rule->match, tuple); + if (err < 0) + goto err_flow_match; + + num_actions = flowtable->type->action(net, flow, dir, flow_rule); + if (num_actions < 0) + goto err_flow_match; + + flow_rule->rule->action.num_entries = num_actions; + + return flow_rule; + +err_flow_match: + kfree(flow_rule->rule); +err_flow_rule: + kfree(flow_rule); +err_flow: + return NULL; +} + +static void __nf_flow_offload_destroy(struct nf_flow_rule *flow_rule) +{ + struct flow_action_entry *entry; + int i; + + for (i = 0; i < flow_rule->rule->action.num_entries; i++) { + entry = &flow_rule->rule->action.entries[i]; + if (entry->id != FLOW_ACTION_REDIRECT) + continue; + + dev_put(entry->dev); + } + kfree(flow_rule->rule); + kfree(flow_rule); +} + +static void nf_flow_offload_destroy(struct nf_flow_rule *flow_rule[]) +{ + int i; + + for (i = 0; i < FLOW_OFFLOAD_DIR_MAX; i++) + __nf_flow_offload_destroy(flow_rule[i]); +} + +static int nf_flow_offload_alloc(const struct flow_offload_work *offload, + struct nf_flow_rule *flow_rule[]) +{ + struct net *net = read_pnet(&offload->flowtable->net); + + flow_rule[0] = nf_flow_offload_rule_alloc(net, offload, + FLOW_OFFLOAD_DIR_ORIGINAL); + if (!flow_rule[0]) + return -ENOMEM; + + flow_rule[1] = nf_flow_offload_rule_alloc(net, offload, + FLOW_OFFLOAD_DIR_REPLY); + if (!flow_rule[1]) { + __nf_flow_offload_destroy(flow_rule[0]); + return -ENOMEM; + } + + return 0; +} + +static void nf_flow_offload_init(struct flow_cls_offload *cls_flow, + __be16 proto, int priority, + enum flow_cls_command cmd, + const struct flow_offload_tuple *tuple, + struct netlink_ext_ack *extack) +{ + cls_flow->common.protocol = proto; + cls_flow->common.prio = priority; + cls_flow->common.extack = extack; + cls_flow->command = cmd; + cls_flow->cookie = (unsigned long)tuple; +} + +static int flow_offload_tuple_add(struct flow_offload_work *offload, + struct nf_flow_rule *flow_rule, + enum flow_offload_tuple_dir dir) +{ + struct nf_flowtable *flowtable = offload->flowtable; + struct flow_cls_offload cls_flow = {}; + struct flow_block_cb *block_cb; + struct netlink_ext_ack extack; + __be16 proto = ETH_P_ALL; + int err, i = 0; + + nf_flow_offload_init(&cls_flow, proto, offload->priority, + FLOW_CLS_REPLACE, + &offload->flow->tuplehash[dir].tuple, &extack); + cls_flow.rule = flow_rule->rule; + + list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) { + err = block_cb->cb(TC_SETUP_FT, &cls_flow, + block_cb->cb_priv); + if (err < 0) + continue; + + i++; + } + + return i; +} + +static void flow_offload_tuple_del(struct flow_offload_work *offload, + enum flow_offload_tuple_dir dir) +{ + struct nf_flowtable *flowtable = offload->flowtable; + struct flow_cls_offload cls_flow = {}; + struct flow_block_cb *block_cb; + struct netlink_ext_ack extack; + __be16 proto = ETH_P_ALL; + + nf_flow_offload_init(&cls_flow, proto, offload->priority, + FLOW_CLS_DESTROY, + &offload->flow->tuplehash[dir].tuple, &extack); + + list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) + block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + + offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD; +} + +static int flow_offload_rule_add(struct flow_offload_work *offload, + struct nf_flow_rule *flow_rule[]) +{ + int ok_count = 0; + + ok_count += flow_offload_tuple_add(offload, flow_rule[0], + FLOW_OFFLOAD_DIR_ORIGINAL); + ok_count += flow_offload_tuple_add(offload, flow_rule[1], + FLOW_OFFLOAD_DIR_REPLY); + if (ok_count == 0) + return -ENOENT; + + return 0; +} + +static int flow_offload_work_add(struct flow_offload_work *offload) +{ + struct nf_flow_rule *flow_rule[FLOW_OFFLOAD_DIR_MAX]; + int err; + + err = nf_flow_offload_alloc(offload, flow_rule); + if (err < 0) + return -ENOMEM; + + err = flow_offload_rule_add(offload, flow_rule); + + nf_flow_offload_destroy(flow_rule); + + return err; +} + +static void flow_offload_work_del(struct flow_offload_work *offload) +{ + flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL); + flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); +} + +static void flow_offload_tuple_stats(struct flow_offload_work *offload, + enum flow_offload_tuple_dir dir, + struct flow_stats *stats) +{ + struct nf_flowtable *flowtable = offload->flowtable; + struct flow_cls_offload cls_flow = {}; + struct flow_block_cb *block_cb; + struct netlink_ext_ack extack; + __be16 proto = ETH_P_ALL; + + nf_flow_offload_init(&cls_flow, proto, offload->priority, + FLOW_CLS_STATS, + &offload->flow->tuplehash[dir].tuple, &extack); + + list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) + block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + memcpy(stats, &cls_flow.stats, sizeof(*stats)); +} + +static void flow_offload_work_stats(struct flow_offload_work *offload) +{ + struct flow_stats stats[FLOW_OFFLOAD_DIR_MAX] = {}; + u64 lastused; + + flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_ORIGINAL, &stats[0]); + flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, &stats[1]); + + lastused = max_t(u64, stats[0].lastused, stats[1].lastused); + offload->flow->timeout = max_t(u64, offload->flow->timeout, + lastused + NF_FLOW_TIMEOUT); +} + +static void flow_offload_work_handler(struct work_struct *work) +{ + struct flow_offload_work *offload, *next; + LIST_HEAD(offload_pending_list); + int ret; + + spin_lock_bh(&flow_offload_pending_list_lock); + list_replace_init(&flow_offload_pending_list, &offload_pending_list); + spin_unlock_bh(&flow_offload_pending_list_lock); + + list_for_each_entry_safe(offload, next, &offload_pending_list, list) { + switch (offload->cmd) { + case FLOW_CLS_REPLACE: + ret = flow_offload_work_add(offload); + if (ret < 0) + offload->flow->flags &= ~FLOW_OFFLOAD_HW; + break; + case FLOW_CLS_DESTROY: + flow_offload_work_del(offload); + break; + case FLOW_CLS_STATS: + flow_offload_work_stats(offload); + break; + default: + WARN_ON_ONCE(1); + } + list_del(&offload->list); + kfree(offload); + } +} + +static void flow_offload_queue_work(struct flow_offload_work *offload) +{ + spin_lock_bh(&flow_offload_pending_list_lock); + list_add_tail(&offload->list, &flow_offload_pending_list); + spin_unlock_bh(&flow_offload_pending_list_lock); + + schedule_work(&nf_flow_offload_work); +} + +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + struct flow_offload_work *offload; + + offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + if (!offload) + return; + + offload->cmd = FLOW_CLS_REPLACE; + offload->flow = flow; + offload->priority = flowtable->priority; + offload->flowtable = flowtable; + flow->flags |= FLOW_OFFLOAD_HW; + + flow_offload_queue_work(offload); +} + +void nf_flow_offload_del(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + struct flow_offload_work *offload; + + offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + if (!offload) + return; + + offload->cmd = FLOW_CLS_DESTROY; + offload->flow = flow; + offload->flow->flags |= FLOW_OFFLOAD_HW_DYING; + offload->flowtable = flowtable; + + flow_offload_queue_work(offload); +} + +void nf_flow_offload_stats(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + struct flow_offload_work *offload; + s64 delta; + + delta = flow->timeout - jiffies; + if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10) || + flow->flags & FLOW_OFFLOAD_HW_DYING) + return; + + offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + if (!offload) + return; + + offload->cmd = FLOW_CLS_STATS; + offload->flow = flow; + offload->flowtable = flowtable; + + flow_offload_queue_work(offload); +} + +void nf_flow_table_offload_flush(struct nf_flowtable *flowtable) +{ + if (flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD) + flush_work(&nf_flow_offload_work); +} + +static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, + struct flow_block_offload *bo, + enum flow_block_command cmd) +{ + struct flow_block_cb *block_cb, *next; + int err = 0; + + switch (cmd) { + case FLOW_BLOCK_BIND: + list_splice(&bo->cb_list, &flowtable->flow_block.cb_list); + break; + case FLOW_BLOCK_UNBIND: + list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + } + break; + default: + WARN_ON_ONCE(1); + err = -EOPNOTSUPP; + } + + return err; +} + +int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + int err; + + if (!(flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD)) + return 0; + + bo.net = dev_net(dev); + bo.block = &flowtable->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + if (err < 0) + return err; + + return nf_flow_table_block_setup(flowtable, &bo, cmd); +} +EXPORT_SYMBOL_GPL(nf_flow_table_offload_setup); + +int nf_flow_table_offload_init(void) +{ + INIT_WORK(&nf_flow_offload_work, flow_offload_work_handler); + + return 0; +} + +void nf_flow_table_offload_exit(void) +{ + struct flow_offload_work *offload, *next; + LIST_HEAD(offload_pending_list); + + cancel_work_sync(&nf_flow_offload_work); + + list_for_each_entry_safe(offload, next, &offload_pending_list, list) { + list_del(&offload->list); + kfree(offload); + } +} -- cgit v1.2.3 From 30aad41721e087babcf27c5192474724d555936c Mon Sep 17 00:00:00 2001 From: Danit Goldberg Date: Wed, 6 Nov 2019 15:30:07 +0200 Subject: net/core: Add support for getting VF GUIDs Introduce a new ndo: ndo_get_vf_guid, to get from the net device the port and node GUID. New applications can choose to use this interface to show GUIDs with iproute2 with commands such as: - ip link show ib4 ib4: mtu 4092 qdisc noop state DOWN mode DEFAULT group default qlen 256 link/infiniband 00:00:0a:2d:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:44:36:8d brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff vf 0 link/infiniband 00:00:0a:2d:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:44:36:8d brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff, spoof checking off, NODE_GUID 22:44:33:00:33:11:00:33, PORT_GUID 10:21:33:12:00:11:22:10, link-state disable, trust off, query_rss off Signed-off-by: Danit Goldberg Acked-by: David Ahern Signed-off-by: Leon Romanovsky --- include/linux/netdevice.h | 4 ++++ net/core/rtnetlink.c | 14 ++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9eda1c31d1f7..379338239e49 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1316,6 +1316,10 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_get_vf_guid)(struct net_device *dev, + int vf, + struct ifla_vf_guid *node_guid, + struct ifla_vf_guid *port_guid); int (*ndo_set_vf_guid)(struct net_device *dev, int vf, u64 guid, int guid_type); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1ee6460f8275..93791dad3e31 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1204,6 +1204,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, struct ifla_vf_mac vf_mac; struct ifla_vf_broadcast vf_broadcast; struct ifla_vf_info ivi; + struct ifla_vf_guid node_guid; + struct ifla_vf_guid port_guid; memset(&ivi, 0, sizeof(ivi)); @@ -1270,6 +1272,18 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, nla_put(skb, IFLA_VF_TRUST, sizeof(vf_trust), &vf_trust)) goto nla_put_vf_failure; + + memset(&node_guid, 0, sizeof(node_guid)); + memset(&port_guid, 0, sizeof(port_guid)); + if (dev->netdev_ops->ndo_get_vf_guid && + !dev->netdev_ops->ndo_get_vf_guid(dev, vfs_num, &node_guid, + &port_guid)) { + if (nla_put(skb, IFLA_VF_IB_NODE_GUID, sizeof(node_guid), + &node_guid) || + nla_put(skb, IFLA_VF_IB_PORT_GUID, sizeof(port_guid), + &port_guid)) + goto nla_put_vf_failure; + } vfvlanlist = nla_nest_start_noflag(skb, IFLA_VF_VLAN_LIST); if (!vfvlanlist) goto nla_put_vf_failure; -- cgit v1.2.3 From 501a90c945103e8627406763dac418f20f3837b2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Dec 2019 20:43:46 -0800 Subject: inet: protect against too small mtu values. syzbot was once again able to crash a host by setting a very small mtu on loopback device. Let's make inetdev_valid_mtu() available in include/net/ip.h, and use it in ip_setup_cork(), so that we protect both ip_append_page() and __ip_append_data() Also add a READ_ONCE() when the device mtu is read. Pairs this lockless read with one WRITE_ONCE() in __dev_set_mtu(), even if other code paths might write over this field. Add a big comment in include/linux/netdevice.h about dev->mtu needing READ_ONCE()/WRITE_ONCE() annotations. Hopefully we will add the missing ones in followup patches. [1] refcount_t: saturated; leaking memory. WARNING: CPU: 0 PID: 9464 at lib/refcount.c:22 refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 9464 Comm: syz-executor850 Not tainted 5.4.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 panic+0x2e3/0x75c kernel/panic.c:221 __warn.cold+0x2f/0x3e kernel/panic.c:582 report_bug+0x289/0x300 lib/bug.c:195 fixup_bug arch/x86/kernel/traps.c:174 [inline] fixup_bug arch/x86/kernel/traps.c:169 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:267 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:286 invalid_op+0x23/0x30 arch/x86/entry/entry_64.S:1027 RIP: 0010:refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22 Code: 06 31 ff 89 de e8 c8 f5 e6 fd 84 db 0f 85 6f ff ff ff e8 7b f4 e6 fd 48 c7 c7 e0 71 4f 88 c6 05 56 a6 a4 06 01 e8 c7 a8 b7 fd <0f> 0b e9 50 ff ff ff e8 5c f4 e6 fd 0f b6 1d 3d a6 a4 06 31 ff 89 RSP: 0018:ffff88809689f550 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff815e4336 RDI: ffffed1012d13e9c RBP: ffff88809689f560 R08: ffff88809c50a3c0 R09: fffffbfff15d31b1 R10: fffffbfff15d31b0 R11: ffffffff8ae98d87 R12: 0000000000000001 R13: 0000000000040100 R14: ffff888099041104 R15: ffff888218d96e40 refcount_add include/linux/refcount.h:193 [inline] skb_set_owner_w+0x2b6/0x410 net/core/sock.c:1999 sock_wmalloc+0xf1/0x120 net/core/sock.c:2096 ip_append_page+0x7ef/0x1190 net/ipv4/ip_output.c:1383 udp_sendpage+0x1c7/0x480 net/ipv4/udp.c:1276 inet_sendpage+0xdb/0x150 net/ipv4/af_inet.c:821 kernel_sendpage+0x92/0xf0 net/socket.c:3794 sock_sendpage+0x8b/0xc0 net/socket.c:936 pipe_to_sendpage+0x2da/0x3c0 fs/splice.c:458 splice_from_pipe_feed fs/splice.c:512 [inline] __splice_from_pipe+0x3ee/0x7c0 fs/splice.c:636 splice_from_pipe+0x108/0x170 fs/splice.c:671 generic_splice_sendpage+0x3c/0x50 fs/splice.c:842 do_splice_from fs/splice.c:861 [inline] direct_splice_actor+0x123/0x190 fs/splice.c:1035 splice_direct_to_actor+0x3b4/0xa30 fs/splice.c:990 do_splice_direct+0x1da/0x2a0 fs/splice.c:1078 do_sendfile+0x597/0xd00 fs/read_write.c:1464 __do_sys_sendfile64 fs/read_write.c:1525 [inline] __se_sys_sendfile64 fs/read_write.c:1511 [inline] __x64_sys_sendfile64+0x1dd/0x220 fs/read_write.c:1511 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x441409 Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fffb64c4f78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441409 RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000005 RBP: 0000000000073b8a R08: 0000000000000010 R09: 0000000000000010 R10: 0000000000010001 R11: 0000000000000246 R12: 0000000000402180 R13: 0000000000402210 R14: 0000000000000000 R15: 0000000000000000 Kernel Offset: disabled Rebooting in 86400 seconds.. Fixes: 1470ddf7f8ce ("inet: Remove explicit write references to sk/inet in ip_append_data") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ include/net/ip.h | 5 +++++ net/core/dev.c | 3 ++- net/ipv4/devinet.c | 5 ----- net/ipv4/ip_output.c | 13 ++++++++----- 5 files changed, 20 insertions(+), 11 deletions(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cf0923579af4..9ef20389622d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1881,6 +1881,11 @@ struct net_device { unsigned char if_port; unsigned char dma; + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ unsigned int mtu; unsigned int min_mtu; unsigned int max_mtu; diff --git a/include/net/ip.h b/include/net/ip.h index 02d68e346f67..5b317c9f4470 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -760,4 +760,9 @@ int ip_misc_proc_init(void); int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack); +static inline bool inetdev_valid_mtu(unsigned int mtu) +{ + return likely(mtu >= IPV4_MIN_MTU); +} + #endif /* _IP_H */ diff --git a/net/core/dev.c b/net/core/dev.c index e7c027fb4808..2c277b8aba38 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8188,7 +8188,8 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); - dev->mtu = new_mtu; + /* Pairs with all the lockless reads of dev->mtu in the stack */ + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a4b5bd4d2c89..e4632bd2026d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1496,11 +1496,6 @@ skip: } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= IPV4_MIN_MTU; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9d83cb320dcb..14db1e0b8a6e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1258,15 +1258,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; cork->gso_size = ipc->gso_size; + cork->dst = &rt->dst; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; -- cgit v1.2.3 From 1f26c0d3d24125992ab0026b0dab16c08df947c7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 16 Dec 2019 18:52:45 -0800 Subject: net: fix kernel-doc warning in Fix missing '*' kernel-doc notation that causes this warning: ../include/linux/netdevice.h:1779: warning: bad line: spinlock Fixes: ab92d68fc22f ("net: core: add generic lockdep keys") Signed-off-by: Randy Dunlap Cc: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/netdevice.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ef20389622d..ae5e260911e2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1775,7 +1775,7 @@ enum netdev_priv_flags { * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock - spinlock + * spinlock * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * @qdisc_xmit_lock_key: lockdep class annotating * netdev_queue->_xmit_lock spinlock -- cgit v1.2.3